This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.
August 2002
·
73 Reads
·
5 Citations
The aim of this work is to study how a pitch detection algorithm can help in the task of locating solos in a musical excerpt. Output parameters of the pitch detection algorithm are studied, and enhancements for the task of solo location are proposed. A solo is defined as a section of a piece where an instrument is in foreground compared to the other instrument and to other section of the piece. 1
101 Reads
·
8 Citations
This paper presents an application for performing melodic transformations to monophonic audio phrases. The system first extracts a melodic description from the audio. This description is presented to the user and can be stored and loaded in a MPEG-7 based format. A set of high-level transformations can then be applied to the melodic description. These high-level transformations are mapped into a set of low-level signal transformations and then applied to the audio signal. The algorithms for description extraction and audio transformation are also presented.
... Automatic melody extraction methods represent the first step to develop systems for automatic transcription (Klapuri and Davy 2006), melodic retrieval (e.g. query by humming (Hu and Dannenberg 2002)) or transformation (Gómez, Peterschmitt, et al. 2003). Further applications deal with the removal of the lead instrument from a polyphonic music recording, since the identification of the pitches from the melody is helpful to guide source separation algorithms (Durrieu, Richard, et al. 2010;Marxer 2013). ...
